Create can_be_used_for_file_upload_app.py

can_be_used_for_file_upload_app.py

@@ -0,0 +1,130 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import (
+    accuracy_score, precision_score, recall_score, f1_score,
+    confusion_matrix, classification_report
+)
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+def train_and_evaluate_model(csv_data=None):
+    # Step 1: Generate synthetic dataset if no CSV data is provided
+    if csv_data is None:
+        np.random.seed(42)
+        n_records = 10000
+        data = {
+            'pe_ratio': np.random.uniform(5, 50, n_records),
+            'de_ratio': np.random.uniform(0.1, 3.0, n_records),
+            'roe': np.random.uniform(5, 40, n_records),
+            'market_cap': np.random.uniform(500, 100000, n_records),
+            'dividend_yield': np.random.uniform(0.5, 5.0, n_records),
+            'stock_rating': np.random.choice(['Buy', 'Hold', 'Sell'], n_records, p=[0.4, 0.4, 0.2])
+        }
+
+        df = pd.DataFrame(data)
+    else:
+        # Step 1: If CSV data is provided, use it
+        df = pd.read_csv(csv_data.name)
+
+    # Step 2: Prepare data
+    X = df.drop('stock_rating', axis=1)
+    y = df['stock_rating']
+
+    # Step 3: Encode target
+    le = LabelEncoder()
+    y_encoded = le.fit_transform(y)
+
+    # Step 4: Train/test split
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y_encoded, test_size=0.3, random_state=42, stratify=y_encoded
+    )
+
+    # Step 5: Feature scaling
+    scaler = StandardScaler()
+    X_train_scaled = scaler.fit_transform(X_train)
+    X_test_scaled = scaler.transform(X_test)
+
+    # Step 6: Train model
+    model = RandomForestClassifier(random_state=42)
+    model.fit(X_train_scaled, y_train)
+
+    # Step 7: Predict
+    y_pred = model.predict(X_test_scaled)
+
+    # Step 8: Decode labels
+    y_test_labels = le.inverse_transform(y_test)
+    y_pred_labels = le.inverse_transform(y_pred)
+
+    # Step 9: Metrics
+    acc = accuracy_score(y_test_labels, y_pred_labels)
+    prec = precision_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
+    rec = recall_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
+    f1 = f1_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
+    
+    # Step 10: Create Classification Report as DataFrame (with zero_division fix)
+    report_dict = classification_report(y_test_labels, y_pred_labels, output_dict=True, zero_division=0)
+    report_df = pd.DataFrame(report_dict).transpose().round(2)
+
+    # Step 11: Plot classification report as table with grid
+    fig, ax = plt.subplots(figsize=(8, 4))
+    ax.axis('off')
+    tbl = ax.table(
+        cellText=report_df.values,
+        colLabels=report_df.columns,
+        rowLabels=report_df.index,
+        cellLoc='center',
+        loc='center'
+    )
+    tbl.auto_set_font_size(False)
+    tbl.set_fontsize(10)
+    tbl.scale(1.2, 1.2)
+    for key, cell in tbl.get_celld().items():
+        cell.set_linewidth(0.8)
+    cr_path = "classification_report.png"
+    plt.savefig(cr_path, bbox_inches='tight')
+    plt.close()
+
+    # Step 12: Confusion matrix
+    cm = confusion_matrix(y_test_labels, y_pred_labels, labels=le.classes_)
+    plt.figure(figsize=(6, 5))
+    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues",
+                xticklabels=le.classes_, yticklabels=le.classes_)
+    plt.xlabel("Predicted")
+    plt.ylabel("Actual")
+    plt.title("Confusion Matrix")
+    cm_path = "confusion_matrix.png"
+    plt.savefig(cm_path, bbox_inches='tight')
+    plt.close()
+
+    # Step 13: Return outputs
+    output = f"""
+### ✅ Evaluation Metrics:
+- **Accuracy:** {acc:.2f}
+- **Precision:** {prec:.2f}
+- **Recall:** {rec:.2f}
+- **F1 Score:** {f1:.2f}
+"""
+    return output, cr_path, cm_path
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 Stock Rating Prediction Model Evaluation")
+    gr.Markdown("You can either upload your own CSV file or use synthetic data to evaluate the model.")
+
+    # CSV file input for user data
+    file_input = gr.File(label="Upload CSV File")
+
+    eval_btn = gr.Button("Run Model Evaluation")
+    output_md = gr.Markdown()
+    report_img = gr.Image(type="filepath", label="📊 Classification Report")
+    cm_img = gr.Image(type="filepath", label="📉 Confusion Matrix")
+
+    eval_btn.click(fn=train_and_evaluate_model,
+                   inputs=[file_input],
+                   outputs=[output_md, report_img, cm_img])
+
+demo.launch()